A human-simulated fuzzy membrane approach for the joint controller of walking biped robots

Liu, Xingyang; Zhang, Gexiang; Mastoi, Muhammad Shahid; Neri, Ferrante; Pu, Yang

doi:10.3233/ica-230698

Cited by 11 publications

(5 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Parameters are shown in Table 2: to verify the effectiveness of the innovation subpart and the overall scheme, the verification is carried out in four parts: 1) constraint damping least square method verification; 2) constrained DDPG training results; 3) experiments of a biped robot up and down stairs; 4) experiments of a biped robot walking on discrete terrains. In experiments 3) and 4), our primary focus is to benchmark our approach against the HF control method, which is considered an advanced solution for addressing the specific problem under investigation [26] since it recently displayed a superior performance with respect to state-of-the-art methods, e.g., [75,84,85,86]. By comparing our method with HF, we aimed to demonstrate the effectiveness of our proposed enhancements and validate their impact on improving the existing state-of-the-art solution.…”

Section: Resultsmentioning

confidence: 99%

“…This method integrates the constraints with model-free reinforcement learning, facilitating seamless integration with the previously designed controller. In [26], the HF controller for gait control of a biped robot was introduced. The HF controller addressed the jitter issue during mode switching in human-simulated intelligent controllers using fuzzy algorithms.…”

Section: Problem Statementmentioning

confidence: 99%

“…In our recent research, we have made significant progress in enabling the dynamic walking of robots through two essential steps [26]. Firstly, we implemented an interpolation-based method to plan the trajectory of footstep locations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep deterministic policy gradient with constraints for gait optimisation of biped robots

Liu,

Rong,

Neri

et al. 2024

ICA

Self Cite

View full text Add to dashboard Cite

In this paper, we propose a novel Reinforcement Learning (RL) algorithm for robotic motion control, that is, a constrained Deep Deterministic Policy Gradient (DDPG) deviation learning strategy to assist biped robots in walking safely and accurately. The previous research on this topic highlighted the limitations in the controller’s ability to accurately track foot placement on discrete terrains and the lack of consideration for safety concerns. In this study, we address these challenges by focusing on ensuring the overall system’s safety. To begin with, we tackle the inverse kinematics problem by introducing constraints to the damping least squares method. This enhancement not only addresses singularity issues but also guarantees safe ranges for joint angles, thus ensuring the stability and reliability of the system. Based on this, we propose the adoption of the constrained DDPG method to correct controller deviations. In constrained DDPG, we incorporate a constraint layer into the Actor network, incorporating joint deviations as state inputs. By conducting offline training within the range of safe angles, it serves as a deviation corrector. Lastly, we validate the effectiveness of our proposed approach by conducting dynamic simulations using the CRANE biped robot. Through comprehensive assessments, including singularity analysis, constraint effectiveness evaluation, and walking experiments on discrete terrains, we demonstrate the superiority and practicality of our approach in enhancing walking performance while ensuring safety. Overall, our research contributes to the advancement of biped robot locomotion by addressing gait optimisation from multiple perspectives, including singularity handling, safety constraints, and deviation learning.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Problem Statementmentioning

confidence: 99%

See 1 more Smart Citation

Deep deterministic policy gradient with constraints for gait optimisation of biped robots

Liu,

Rong,

Neri

et al. 2024

ICA

Self Cite

View full text Add to dashboard Cite

show abstract

“…For 3D reconstruction, it can provide interpretable reconstruction process step-by-step by simulating human modelers. The human-simulated method can help solve many problems in engineering [49], and may in turn help human modelers become better [50]. In addition, it can train the network according to the reward given by the environment without supervision.…”

Section: Related Workmentioning

confidence: 99%

3D reconstruction based on hierarchical reinforcement learning with transferability

Fan

et al. 2023

ICA

View full text Add to dashboard Cite

3D reconstruction is extremely important in CAD (computer-aided design)/CAE (computer-aided Engineering)/CAM (computer-aided manufacturing). For interpretability, reinforcement learning (RL) is used to reconstruct 3D shapes from images by a series of editing actions. However, typical applications of RL for 3D reconstruction face problems. The search space will increase exponentially with the action space due to the curse of dimensionality, which leads to low performance, especially for complex action spaces in 3D reconstruction. Additionally, most works involve training a specific agent for each shape class without learning related experiences from others. Therefore, we present a hierarchical RL approach with transferability to reconstruct 3D shapes (HRLT3D). First, actions are grouped into macro actions that can be chosen by the top-agent. Second, the task is accordingly decomposed into hierarchically simplified sub-tasks solved by sub-agents. Different from classical hierarchical RL (HRL), we propose a sub-agent based on augmented state space (ASS-Sub-Agent) to replace a set of sub-agents, which can speed up the training process due to shared learning and having fewer parameters. Furthermore, the ASS-Sub-Agent is more easily transferred to data of other classes due to the augmented diverse states and the simplified tasks. The experimental results on typical public dataset show that the proposed HRLT3D performs overwhelmingly better than recent baselines. More impressingly, the experiments also demonstrate the extreme transferability of our approach among data of different classes.

show abstract

“…Falk, M et al pointed out that the competitive effect of industrial clusters led to the intensification of competition among enterprises in the same industry in the cluster area, which prompted enterprises to accelerate the improvement of R&D capabilities and competitiveness [18,19]. According to the innovation theory, innovation capability is a new development capability generated by the enterprise's re-integration of existing production factors [20,21]. On the one hand, innovation can encourage enterprises to develop new products, occupy new markets and expand the scope of business.…”

mentioning

confidence: 99%

The Impact of Industry Clusters on the Performance of High Technology Small and Middle Size Enterprises

et al. 2023

View full text Add to dashboard Cite

Based on the theory of independent innovation and competitive advantage, this paper takes industry cluster as the independent variable, long-term high-technology small and middle size enterprises (high-tech SMEs) performance and short-term high-tech SMEs’ performance as the dependent variable, and introduces independent innovation as the mediator variable to explore the impact of industry cluster on high-tech SMEs’ performance. SPSS22.0 was used to test the reliability and validity of the questionnaire distributed to 310 high-tech SMEs in Sichuan, China. SPSS is used for statistical analysis, integrating data entry, organization, and analysis functions. Its basic functions include data management, statistical analysis, chart analysis, and output management. A confirmatory factor analysis was conducted. Amos 24.0 is the structural equation model analysis software. After using Amos 24.0 to construct the SEM (Structural Equation Modelling) to verify the hypothesis, it was found that industry cluster has a significant positive impact on long-term and short-term high-tech SMEs’ performance, independent innovation has a significant positive impact on long-term and short-term high-tech SMEs’ performance, and independent innovation plays a mediator role in the relationship between industry cluster and high-tech SMEs’ performance. Based on the research results, this paper puts forward the following suggestions: (1) attach importance to independent innovation, introduce relevant technical talents, and improve innovation; and (2) accelerate the formation of clusters to improve the high-tech SMEs’ performance of the whole industry.

show abstract

A human-simulated fuzzy membrane approach for the joint controller of walking biped robots

Cited by 11 publications

References 69 publications

Deep deterministic policy gradient with constraints for gait optimisation of biped robots

Deep deterministic policy gradient with constraints for gait optimisation of biped robots

3D reconstruction based on hierarchical reinforcement learning with transferability

The Impact of Industry Clusters on the Performance of High Technology Small and Middle Size Enterprises

Contact Info

Product

Resources

About